© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48580
    Prev
    Next
    INDEX
    Explanations

    need to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ६
    0.40
     RAS
    0.38
     Squid
    0.38
    桎
    0.37
     Interim
    0.36
     Casc
    0.36
     Trap
    0.36
     Cascade
    0.36
    POSITORY
    0.36
    膈
    0.35
    POSITIVE LOGITS
     loudly
    0.39
     roads
    0.38
     inclement
    0.38
     menacing
    0.38
     കി
    0.37
     luxe
    0.37
     loud
    0.37
    znam
    0.36
    嘴角
    0.36
     louder
    0.36
    Activations Density 0.008%

    No Known Activations